Skip to content

Conversation

HauserA
Copy link
Contributor

@HauserA HauserA commented Jan 27, 2020

Added batch hard loss with soft margin version as in In Defense of the Triplet Loss for Person Re-Identification.

The difference to triplet_semihard_loss is the hard negative and hard positive mining and the option for a soft margin with the softplus-function instead of a hard margin.

@googlebot
Copy link

Thanks for your pull request. It looks like this may be your first contribution to a Google open source project (if not, look below for help). Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

📝 Please visit https://cla.developers.google.com/ to sign.

Once you've signed (or fixed any issues), please reply here with @googlebot I signed it! and we'll verify it.


What to do if you already signed the CLA

Individual signers
Corporate signers

ℹ️ Googlers: Go here for more info.

@HauserA
Copy link
Contributor Author

HauserA commented Jan 28, 2020

@googlebot I signed it!

@googlebot
Copy link

CLAs look good, thanks!

ℹ️ Googlers: Go here for more info.

Copy link
Member

@WindQAQ WindQAQ left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @HauserA, thanks for the contribution!

Generally LGTM. Could you update __init__.py? Also, I would suggest put the tests into triplet_test.py as they belong to the same family. Thank you again!

@HauserA HauserA requested a review from WindQAQ January 28, 2020 18:39

def get_config(self):
config = {
"margin": self.margin,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we also serialize self.soft here?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes

Copy link
Member

@WindQAQ WindQAQ left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you again for the contribution 😃

@WindQAQ WindQAQ merged commit 079899b into tensorflow:master Jan 30, 2020
failure-to-thrive pushed a commit to failure-to-thrive/addons that referenced this pull request Feb 1, 2020
* triplet hard loss

* triplet hard test

* format with black

* FaceNet reference

* spelling correction

* soft margin version

* test for soft margin version

* Update description of loss function

* moved tests into triplet_test.py

* Added triplet_hard_loss, TripletHardLoss to init

* flake8 unused variable

* added typechecks for __init__

* serialize self.soft
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants